© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 2189
    Prev
    Next
    INDEX
    Explanations

    phrases related to moral contrasts, especially 'good vs. bad' and 'right vs. wrong'

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to moral judgment and duality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mud
    -0.72
    etsy
    -0.71
    culosis
    -0.67
    emi
    -0.65
    thur
    -0.62
    nit
    -0.61
    gone
    -0.61
    ª
    -0.60
    zar
    -0.59
    atl
    -0.59
    POSITIVE LOGITS
     alike
    1.47
     respectively
    1.44
     depending
    1.37
    depending
    1.18
     versions
    0.93
     sides
    0.88
     perspectives
    0.84
     inclusive
    0.79
     modes
    0.78
     coasts
    0.76
    Activations Density 0.314%

    No Known Activations